System

Abstract

An object of the system according to the embodiment is to provide a summary according to a knowledge level of a reader and optimize a reading experience.SOLUTION: A system according to an embodiment includes a summary generation unit, a marker function unit, a summary generation unit, and an expression change unit. The summary generation part generates a summary corresponding to the knowledge level of the reader. The marker function unit adds a marker to a specific range of the summary generated by the summary generation unit. The summary generation unit generates a summary of the range marked by the marker function unit. The expression changing unit changes an unclear part of the summary generated by the summary generating unit to a simple expression.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies make it difficult to provide summaries that match the reader's knowledge level, and there is room for improvement in optimizing the reading experience.

[0005] The system according to the embodiment aims to provide summaries according to the reader's knowledge level and optimize the reading experience. [Means for solving the problem]

[0006] The system according to the embodiment includes a summary generation unit, a marker function unit, a summary generation unit, and an expression modification unit. The summary generation unit generates a summary according to the reader's knowledge level. The marker function unit marks specific ranges in the summary generated by the summary generation unit. The summary generation unit generates a summary for the range marked by the marker function unit. The expression modification unit modifies difficult-to-understand parts of the summary generated by the summary generation unit into simpler expressions. [Effects of the Invention]

[0007] The system according to the embodiment can provide summaries according to the reader's knowledge level to optimize the reading experience. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A reading experience optimization system according to an embodiment of the present invention utilizes a generative AI to optimize the e-book reading experience. The reading experience optimization system generates summaries tailored to the reader's knowledge level, highlights specific sections, and simplifies difficult-to-understand parts. It also supports the concurrent reading of multiple books and acquires the user's marker information, which it uses as marketing data for publishing strategies. For example, the reading experience optimization system generates summaries tailored to the reader's knowledge level. The reader's knowledge level is determined based on the reading history and user input within the app. For example, summaries tailored to the reader's level, such as summaries for beginners, intermediate readers, and advanced readers, are generated. Next, the reading experience optimization system uses the app's unique marker function to generate summaries for specific sections of interest to the reader. For example, a reader can highlight specific chapters or paragraphs, generating a summary for that section. Furthermore, the reading experience optimization system uses a generative AI to simplify difficult or confusing sections. For example, the generative AI replaces technical terms and difficult expressions with simpler terms. The reading experience optimization system also supports the concurrent reading of multiple books. For example, by linking points from books previously purchased with the book a reader is currently reading, related information can be referenced efficiently. Finally, the reading experience optimization system acquires user marker information and uses it as marketing data for publishing strategies. For example, analyzing information such as which parts of a book are highly highlighted and which summaries are most frequently read can be used to improve publishing strategies. This allows the reading experience optimization system to provide functions such as generating summaries based on the reader's knowledge level, highlighting specific ranges, simplifying difficult-to-understand sections, supporting parallel reading of multiple books, and acquiring user marker information. For example, readers can read more efficiently by receiving summaries based on their knowledge level. Furthermore, generating summaries based on specific ranges and simplifying difficult-to-understand sections improves comprehension. Furthermore, supporting parallel reading of multiple books allows readers to efficiently reference related information.Finally, obtaining user marker information and using it as marketing data for publishing strategies can help improve publishing strategies.

[0029] A reading experience optimization system according to an embodiment includes a summary generation unit, a marker function unit, and an expression modification unit. The summary generation unit uses a generation AI to generate summaries according to the reader's knowledge level. The reader's knowledge level is determined, for example, based on the reader's reading history within the app or input information from the reader. For example, the summary generation unit generates summaries according to the reader's level, such as summaries for beginners, intermediate readers, and advanced readers. The marker function unit uses the generation AI to mark specific sections of the summary generated by the summary generation unit. For example, a reader can mark specific chapters or paragraphs, generating a summary of that section. The marker function unit allows the reader to efficiently delve deeper into parts of their interest. Furthermore, the marked sections can be easily reread later, improving reading efficiency. The expression modification unit uses the generation AI to change difficult-to-understand parts of the summary generated by the summary generation unit to simpler expressions. For example, the generation AI can replace parts containing technical terms or difficult expressions with simpler words, making it easier for the reader to understand. This allows the reader to smoothly proceed through even difficult content. As a result, the reading experience optimization system according to the embodiment can generate summaries according to the reader's knowledge level, highlight specific ranges, and change difficult-to-understand parts to simpler expressions.

[0030] Furthermore, the reading experience optimization system includes a unit that supports the parallel reading of multiple books. The parallel reading support unit uses generative AI to support the parallel reading of multiple books. For example, by linking points from books a reader has previously purchased with the book they are currently reading, they can efficiently refer to related information. The parallel reading support unit makes it easier for readers to understand the relevance of information even when reading multiple books simultaneously. For example, the parallel reading support unit presents the relevance of the book they are currently reading based on the content of books they have previously read. The parallel reading support unit also extracts the main points of books they have previously read and links them to the book they are currently reading, allowing them to efficiently organize information. This allows readers to efficiently read multiple books by supporting the parallel reading of multiple books.

[0031] Furthermore, the reading experience optimization system includes a unit that acquires user marker information and uses it as data for a publishing strategy. The marketing data acquisition unit uses generative AI to acquire user marker information and uses it as data for a publishing strategy. For example, the marketing data acquisition unit analyzes information such as which parts have been marked with many markers and which summaries are frequently read. The marketing data acquisition unit can use the user marker information to improve the publishing strategy. For example, if a particular chapter or paragraph has been marked with many markers, the marketing data acquisition unit determines that this part is important to readers and reflects this in future publishing strategies. The marketing data acquisition unit also understands readers' interests and collects data to provide content that is attractive to readers. In this way, the user's marker information can be acquired and used as marketing data for a publishing strategy, which can be useful for improving the publishing strategy.

[0032] The summary generation unit can analyze the reader's past reading history and select a summary generation method. The summary generation unit uses generation AI to analyze the reader's past reading history and select the optimal summary generation method. For example, the summary generation unit analyzes the genre of books the reader has read in the past and generates the optimal summary for books of the same genre. The summary generation unit can also analyze the difficulty of books the reader has read in the past and generate the optimal summary for books of the same difficulty level. The summary generation unit can also analyze the ratings of books the reader has read in the past and generate more detailed summaries for highly rated books. In this way, the optimal summary generation method can be selected by analyzing the reader's past reading history.

[0033] The summary generator can customize the content of the summary based on the reader's current areas of interest when generating the summary. The summary generator uses generation AI to customize the content of the summary based on the reader's current areas of interest when generating the summary. For example, the summary generator generates a summary that includes related information based on topics that the reader is currently interested in. The summary generator can also generate a summary that includes related information based on keywords that the reader has recently searched for. The summary generator can also generate a summary that includes related information based on articles or news that the reader has recently read. This makes it possible to provide more relevant summaries by customizing the content of the summary based on the reader's current areas of interest.

[0034] The summary generation unit can select a summary generation means according to the reader's input method when generating a summary. The summary generation unit uses the generation AI to select the optimal summary generation means according to the reader's input method (voice, text, image, etc.) when generating a summary. For example, if the reader uses voice input, the summary generation unit has the generation AI analyze the voice data and generate the optimal summary. Also, if the reader uses text input, the summary generation unit can have the generation AI analyze the text data and generate the optimal summary. Also, if the reader uses image input, the summary generation unit can have the generation AI analyze the image data and generate the optimal summary. This makes it possible to provide a more appropriate summary by selecting the optimal summary generation means according to the reader's input method.

[0035] When generating summaries, the summary generation unit can prioritize generating highly relevant summaries by taking into account the reader's geographical location information. When generating summaries, the summary generation unit uses generation AI to prioritize generating highly relevant summaries by taking into account the reader's geographical location information. For example, if the reader is in a specific area, the summary generation unit can generate a summary that includes information related to that area. Also, if the reader is traveling, the summary generation unit can generate a summary that includes information related to the travel destination. Also, if the reader is in a specific city, the summary generation unit can generate a summary that includes information related to that city. This makes it possible to provide more appropriate summaries by prioritizing the generation of highly relevant summaries by taking into account the reader's geographical location information.

[0036] The summary generation unit can analyze the reader's social media activity when generating a summary and generate a relevant summary. The summary generation unit uses generation AI to analyze the reader's social media activity when generating a summary and generate a relevant summary. For example, the summary generation unit generates a summary that includes related information based on articles that the reader shared on social media. The summary generation unit can also generate a summary that includes related information based on accounts that the reader follows on social media. The summary generation unit can also generate a summary that includes related information based on posts that the reader "liked" on social media. In this way, it is possible to provide relevant summaries by analyzing the reader's social media activity.

[0037] The summary generation unit can customize the summary generation method by reflecting readers' past feedback when generating a summary. The summary generation unit uses generation AI to customize the summary generation method by reflecting readers' past feedback when generating a summary. For example, the summary generation unit generates the optimal summary based on summary generation methods that readers have previously rated highly. The summary generation unit can also generate the optimal summary by avoiding summary generation methods that readers have previously rated poorly. The summary generation unit can also customize the content and presentation of the summary based on feedback provided by readers in the past. This makes it possible to provide more appropriate summaries by reflecting readers' past feedback.

[0038] When the marker function is used, the marker function unit can analyze the reader's past marker history and select the optimal marker display method. When the marker function is used, the marker function unit uses generation AI to analyze the reader's past marker history and select the optimal marker display method. For example, the marker function unit displays the optimal marker based on the marker color and style used by the reader in the past. The marker function unit can also analyze the trends in the places where readers have marked in the past and display markers in related places. The marker function unit can also display the optimal marker based on the display method of markers that the reader has given high ratings to in the past. In this way, the optimal marker display method can be selected by analyzing the reader's past marker history.

[0039] The marker function unit can customize the range of markers based on the reader's current reading situation when using the marker function. The marker function unit uses generation AI to customize the range of markers based on the reader's current reading situation when using the marker function. For example, if a reader is reading a specific chapter, the marker function unit can display markers in ranges related to that chapter. Also, if a reader is concentrating on a specific topic, the marker function unit can display markers in ranges related to that topic. Also, if a reader is searching for a specific keyword, the marker function unit can display markers in ranges related to that keyword. This makes it possible to provide more appropriate markers by customizing the range of markers based on the reader's current reading situation.

[0040] The marker function unit can select the optimal marker display means depending on the reader's input method when using the marker function. The marker function unit uses the generation AI to select the optimal marker display means depending on the reader's input method (voice, text, image, etc.) when using the marker function. For example, if the reader is using voice input, the marker function unit can have the generation AI analyze the voice data and display the optimal marker. Also, if the reader is using text input, the marker function unit can have the generation AI analyze the text data and display the optimal marker. Also, if the reader is using image input, the marker function unit can have the generation AI analyze the image data and display the optimal marker. This makes it possible to provide more appropriate markers by selecting the optimal marker display means depending on the reader's input method.

[0041] When the marker function is used, the marker function unit can prioritize displaying highly relevant markers by taking into consideration the reader's geographical location information. When the marker function is used, the marker function unit uses generation AI to prioritize displaying highly relevant markers by taking into consideration the reader's geographical location information. For example, if the reader is in a specific area, the marker function unit can display markers containing information related to that area. Also, if the reader is traveling, the marker function unit can display markers containing information related to the travel destination. Also, if the reader is in a specific city, the marker function unit can display markers containing information related to that city. This makes it possible to provide more appropriate markers by prioritize displaying highly relevant markers by taking into consideration the reader's geographical location information.

[0042] The marker function unit can analyze the reader's social media activity and display related markers when the marker function is used. The marker function unit uses generation AI to analyze the reader's social media activity and display related markers when the marker function is used. For example, the marker function unit displays markers containing related information based on articles the reader has shared on social media. The marker function unit can also display markers containing related information based on accounts the reader follows on social media. The marker function unit can also display markers containing related information based on posts the reader has "liked" on social media. In this way, related markers can be provided by analyzing the reader's social media activity.

[0043] The marker function unit can customize the marker display method by reflecting readers' past feedback when the marker function is used. The marker function unit uses generation AI to customize the marker display method by reflecting readers' past feedback when the marker function is used. For example, the marker function unit displays the most appropriate marker based on the display method of markers that readers have previously rated highly. The marker function unit can also display the most appropriate marker by avoiding the display method of markers that readers have previously rated poorly. The marker function unit can also customize the content and display method of markers based on feedback provided by readers in the past. This makes it possible to provide more appropriate markers by reflecting readers' past feedback.

[0044] The expression modification unit can customize the expression based on the reader's current level of understanding when changing the expression. The expression modification unit uses the generation AI to customize the expression based on the reader's current level of understanding when changing the expression. For example, if the reader has a low level of understanding of a particular topic, the expression modification unit causes the generation AI to change the expression to a simpler one. Also, if the reader has a high level of understanding of a particular topic, the expression modification unit can cause the generation AI to change the expression to a more detailed one. Also, if the reader has a medium level of understanding of a particular topic, the expression modification unit can cause the generation AI to change the expression to one with an appropriate level of detail. In this way, by customizing the expression based on the reader's current level of understanding, more appropriate expression can be provided.

[0045] The expression change unit can select the optimal expression change means depending on the reader's input method when changing an expression. The expression change unit uses the generation AI to select the optimal expression change means depending on the reader's input method (voice, text, image, etc.) when changing an expression. For example, if the reader uses voice input, the expression change unit has the generation AI analyze the voice data and change the expression to the optimal expression. Also, if the reader uses text input, the expression change unit can have the generation AI analyze the text data and change the expression to the optimal expression. Also, if the reader uses image input, the generation AI can analyze the image data and change the expression to the optimal expression. In this way, by selecting the optimal expression change means depending on the reader's input method, more appropriate expressions can be provided.

[0046] When changing expressions, the expression change unit can prioritize changing highly relevant expressions taking into account the reader's geographical location information. When changing expressions, the expression change unit uses generation AI to prioritize changing highly relevant expressions taking into account the reader's geographical location information. For example, if the reader is in a specific area, the expression change unit can prioritize changing expressions that include information related to that area. Also, if the reader is traveling, the expression change unit can prioritize changing expressions that include information related to the travel destination. Also, if the reader is in a specific city, the expression change unit can prioritize changing expressions that include information related to that city. In this way, by prioritizing changing highly relevant expressions taking into account the reader's geographical location information, more appropriate expressions can be provided.

[0047] The expression change unit can analyze the reader's social media activity and change the relevant expression when changing the expression. The expression change unit uses generative AI to analyze the reader's social media activity and change the relevant expression when changing the expression. For example, the expression change unit changes the expression including relevant information based on articles the reader shared on social media. The expression change unit can also change the expression including relevant information based on accounts the reader follows on social media. The expression change unit can also change the expression including relevant information based on posts the reader "liked" on social media. In this way, relevant expression can be provided by analyzing the reader's social media activity.

[0048] The expression change unit can customize the expression change method by reflecting readers' past feedback when changing expressions. The expression change unit uses a generation AI to customize the expression change method by reflecting readers' past feedback when changing expressions. For example, the expression change unit changes the most appropriate expression based on expression change methods that readers have given high ratings to in the past. The expression change unit can also change the most appropriate expression by avoiding expression change methods that readers have given low ratings to in the past. The expression change unit can also customize the content of the expression and the change method based on feedback provided by readers in the past. This makes it possible to provide more appropriate expressions by reflecting readers' past feedback.

[0049] The parallel reading support unit can analyze the reader's past reading history and select the optimal support method when supporting parallel reading. The parallel reading support unit uses generative AI to analyze the reader's past reading history and select the optimal support method when supporting parallel reading. For example, the parallel reading support unit analyzes the genre of books the reader has read in the past and provides the optimal support for books of the same genre. The parallel reading support unit can also analyze the difficulty level of books the reader has read in the past and provide the optimal support for books of the same difficulty level. The parallel reading support unit can also analyze the ratings of books the reader has read in the past and provide more detailed support for highly rated books. In this way, the optimal support method can be selected by analyzing the reader's past reading history.

[0050] The parallel reading support unit can customize the support content based on the reader's current reading situation when supporting parallel reading. The parallel reading support unit uses generative AI to customize the support content based on the reader's current reading situation when supporting parallel reading. For example, if the reader is reading a specific chapter, the parallel reading support unit can provide information related to that chapter. Also, if the reader is concentrating on a specific topic, the parallel reading support unit can provide information related to that topic. Also, if the reader is searching for a specific keyword, the parallel reading support unit can provide information related to that keyword. This allows the support content to be customized based on the reader's current reading situation, making it possible to provide more appropriate support.

[0051] The parallel reading support unit can prioritize providing highly relevant support by taking into account the reader's geographical location information when supporting parallel reading. The parallel reading support unit uses generation AI to prioritize providing highly relevant support by taking into account the reader's geographical location information when supporting parallel reading. For example, if the reader is in a specific area, the parallel reading support unit can provide information related to that area. Also, if the reader is traveling, the parallel reading support unit can provide information related to the travel destination. Also, if the reader is in a specific city, the parallel reading support unit can provide information related to that city. This makes it possible to provide more appropriate support by prioritizing highly relevant support by taking into account the reader's geographical location information.

[0052] The parallel reading support unit can analyze the reader's social media activity and provide relevant support during parallel reading support. The parallel reading support unit uses generative AI to analyze the reader's social media activity and provide relevant support during parallel reading support. For example, the parallel reading support unit can provide relevant information based on articles the reader has shared on social media. The parallel reading support unit can also provide relevant information based on accounts the reader follows on social media. The parallel reading support unit can also provide relevant information based on posts the reader has "liked" on social media. In this way, relevant support can be provided by analyzing the reader's social media activity.

[0053] When acquiring marketing data, the marketing data acquisition unit can analyze the reader's past marker history and select the optimal data acquisition method. When acquiring marketing data, the marketing data acquisition unit uses the generation AI to analyze the reader's past marker history and select the optimal data acquisition method. For example, the marketing data acquisition unit acquires optimal data based on the marker colors and styles used by the reader in the past. The marketing data acquisition unit can also analyze trends in areas that readers have highlighted in the past and acquire related data. The marketing data acquisition unit can also acquire optimal data based on data on markers that readers have given high ratings to in the past. In this way, the optimal data acquisition method can be selected by analyzing the reader's past marker history.

[0054] The marketing data acquisition unit can customize the data acquisition content based on the reader's current reading status when acquiring marketing data. The marketing data acquisition unit uses the generation AI to customize the data acquisition content based on the reader's current reading status when acquiring marketing data. For example, if a reader is reading a specific chapter, the marketing data acquisition unit can acquire data related to that chapter. Also, if a reader is concentrating on a specific topic, the marketing data acquisition unit can also acquire data related to that topic. Also, if a reader is searching for a specific keyword, the marketing data acquisition unit can acquire data related to that keyword. In this way, by customizing the data acquisition content based on the reader's current reading status, more appropriate data can be acquired.

[0055] The marketing data acquisition unit can analyze readers' social media activities and acquire related data when acquiring marketing data. The marketing data acquisition unit uses generative AI to analyze readers' social media activities and acquire related data when acquiring marketing data. For example, the marketing data acquisition unit acquires related data based on articles shared by readers on social media. The marketing data acquisition unit can also acquire related data based on accounts that readers follow on social media. The marketing data acquisition unit can also acquire related data based on posts that readers "like" on social media. In this way, related data can be acquired by analyzing readers' social media activities.

[0056] The marketing data acquisition unit can customize the data acquisition method by reflecting readers' past feedback when acquiring marketing data. The marketing data acquisition unit uses generative AI to customize the data acquisition method by reflecting readers' past feedback when acquiring marketing data. For example, the marketing data acquisition unit acquires optimal data based on data acquisition methods that readers have given high ratings to in the past. The marketing data acquisition unit can also acquire optimal data by avoiding data acquisition methods that readers have given low ratings to in the past. The marketing data acquisition unit can also customize the content of data and the acquisition method based on feedback provided by readers in the past. This makes it possible to acquire more appropriate data by reflecting readers' past feedback.

[0057] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0058] The reading experience optimization system can further include a speed adjustment unit that measures the reader's reading speed and adjusts the level of detail in the summary according to the speed. For example, if the reader is reading quickly, the speed adjustment unit can use a generation AI to generate a concise summary that covers the main points. On the other hand, if the reader is reading slowly, the speed adjustment unit can also generate a detailed summary. Furthermore, if the reader stops at a particular point, it can provide additional information related to that point. This makes it possible to provide a more appropriate reading experience by adjusting the level of detail in the summary according to the reader's reading speed.

[0059] The reading experience optimization system may further include an eye-tracking unit that acquires eye-tracking data of the reader and adjusts the summary generation method based on the eye movements. For example, if the reader focuses their eyes on a particular passage, the eye-tracking unit may generate a detailed summary related to that passage. If the reader moves their eyes frequently, the eye-tracking unit may generate a concise summary that covers the main points. Furthermore, if the reader fixates their eyes for a long time, the eye-tracking unit may provide additional information related to that passage. In this way, a more appropriate reading experience can be provided by adjusting the summary generation method based on the reader's eye movements.

[0060] The reading experience optimization system can further include an environment detection unit that detects the reader's reading environment and adjusts the summary generation method according to the environment. For example, if the reader is in a quiet environment, the environment detection unit can use the generation AI to generate a detailed summary. If the reader is in a noisy environment, the environment detection unit can also generate a concise summary. Furthermore, if the reader is on the move, the environment detection unit can also generate a summary that focuses on the main points. This allows for a more appropriate reading experience by adjusting the summary generation method according to the reader's reading environment.

[0061] The reading experience optimization system can further include a device detection unit that detects the device usage status of the reader and adjusts the summary generation method according to the usage status. For example, if the reader is using a smartphone, the device detection unit can use the generation AI to generate a concise summary. If the reader is using a tablet, the device detection unit can also generate a detailed summary. Furthermore, if the reader is using a PC, the device detection unit can also generate a visually rich summary. This makes it possible to provide a more appropriate reading experience by adjusting the summary generation method according to the device usage status of the reader.

[0062] The reading experience optimization system can further include a cloud synchronization unit that stores the reader's reading history on the cloud and makes it accessible from other devices. For example, if a reader continues reading a book on a tablet after having been reading it on a smartphone, the cloud synchronization unit synchronizes the reading history so that the reader can resume reading from the same place. The cloud synchronization unit can also synchronize the reading history if the reader continues reading a book on a smartphone after having been reading it on a computer. Furthermore, if the reader purchases a new device, the cloud synchronization unit can synchronize the reading history. This allows the reader's reading history to be stored on the cloud and be accessible from other devices, providing a more convenient reading experience.

[0063] The reading experience optimization system can further include a time adjustment unit that measures the reader's reading time and adjusts the summary generation method according to the time. For example, if the reader reads for a short time, the time adjustment unit uses a generation AI to generate a concise summary that covers the main points. On the other hand, if the reader reads for a long time, the time adjustment unit can also generate a detailed summary. Furthermore, if the reader reads at a specific time of day, it can also generate a summary appropriate for that time of day. This makes it possible to provide a more appropriate reading experience by adjusting the summary generation method according to the reader's reading time.

[0064] The reading experience optimization system can further include a habit learning unit that learns the reader's reading habits and adjusts the summary generation method based on the habits. For example, if a reader reads at a specific time every day, the habit learning unit can generate summaries that are optimal for that time. Also, if a reader reads for long periods on weekends, the habit learning unit can generate detailed summaries. Furthermore, if a reader prefers to read books of a specific genre, it can generate summaries that are appropriate for that genre. In this way, a more appropriate reading experience can be provided by adjusting the summary generation method based on the reader's reading habits.

[0065] The processing flow of the first embodiment will be briefly explained below.

[0066] Step 1: The summary generator uses AI to generate summaries tailored to the reader's knowledge level. The reader's knowledge level is determined based on their reading history within the app and their input information. For example, summaries tailored to the reader's level are generated, such as summaries for beginners, intermediate readers, and advanced readers. Step 2: The marker function uses the generation AI to highlight specific sections of the summary generated by the summary generator. For example, if a reader highlights a specific chapter or paragraph, a summary of that section will be generated. This allows the reader to efficiently dig deeper into the parts of the text that interest them and easily reread them later. Step 3: The expression modification unit uses the generation AI to change any difficult-to-understand parts of the summary generated by the summary generation unit into simpler expressions. For example, the generation AI can replace parts containing technical terms or difficult expressions with simpler words, making them easier for readers to understand.

[0067] (Example 2) A reading experience optimization system according to an embodiment of the present invention utilizes a generative AI to optimize the e-book reading experience. The reading experience optimization system generates summaries tailored to the reader's knowledge level, highlights specific sections, and simplifies difficult-to-understand parts. It also supports the concurrent reading of multiple books and acquires the user's marker information, which it uses as marketing data for publishing strategies. For example, the reading experience optimization system generates summaries tailored to the reader's knowledge level. The reader's knowledge level is determined based on the reading history and user input within the app. For example, summaries tailored to the reader's level, such as summaries for beginners, intermediate readers, and advanced readers, are generated. Next, the reading experience optimization system uses the app's unique marker function to generate summaries for specific sections of interest to the reader. For example, a reader can highlight specific chapters or paragraphs, generating a summary for that section. Furthermore, the reading experience optimization system uses a generative AI to simplify difficult or confusing sections. For example, the generative AI replaces technical terms and difficult expressions with simpler terms. The reading experience optimization system also supports the concurrent reading of multiple books. For example, by linking points from books previously purchased with the book a reader is currently reading, related information can be referenced efficiently. Finally, the reading experience optimization system acquires user marker information and uses it as marketing data for publishing strategies. For example, analyzing information such as which parts of a book are highly highlighted and which summaries are most frequently read can be used to improve publishing strategies. This allows the reading experience optimization system to provide functions such as generating summaries based on the reader's knowledge level, highlighting specific ranges, simplifying difficult-to-understand sections, supporting parallel reading of multiple books, and acquiring user marker information. For example, readers can read more efficiently by receiving summaries based on their knowledge level. Furthermore, generating summaries based on specific ranges and simplifying difficult-to-understand sections improves comprehension. Furthermore, supporting parallel reading of multiple books allows readers to efficiently reference related information.Finally, obtaining user marker information and using it as marketing data for publishing strategies can help improve publishing strategies.

[0068] A reading experience optimization system according to an embodiment includes a summary generation unit, a marker function unit, and an expression modification unit. The summary generation unit uses a generation AI to generate summaries according to the reader's knowledge level. The reader's knowledge level is determined, for example, based on the reader's reading history within the app or input information from the reader. For example, the summary generation unit generates summaries according to the reader's level, such as summaries for beginners, intermediate readers, and advanced readers. The marker function unit uses the generation AI to mark specific sections of the summary generated by the summary generation unit. For example, a reader can mark specific chapters or paragraphs, generating a summary of that section. The marker function unit allows the reader to efficiently delve deeper into parts of their interest. Furthermore, the marked sections can be easily reread later, improving reading efficiency. The expression modification unit uses the generation AI to change difficult-to-understand parts of the summary generated by the summary generation unit to simpler expressions. For example, the generation AI can replace parts containing technical terms or difficult expressions with simpler words, making it easier for the reader to understand. This allows the reader to smoothly proceed through even difficult content. As a result, the reading experience optimization system according to the embodiment can generate summaries according to the reader's knowledge level, highlight specific ranges, and change difficult-to-understand parts to simpler expressions.

[0069] Furthermore, the reading experience optimization system includes a unit that supports the parallel reading of multiple books. The parallel reading support unit uses generative AI to support the parallel reading of multiple books. For example, by linking points from books a reader has previously purchased with the book they are currently reading, they can efficiently refer to related information. The parallel reading support unit makes it easier for readers to understand the relevance of information even when reading multiple books simultaneously. For example, the parallel reading support unit presents the relevance of the book they are currently reading based on the content of books they have previously read. The parallel reading support unit also extracts the main points of books they have previously read and links them to the book they are currently reading, allowing them to efficiently organize information. This allows readers to efficiently read multiple books by supporting the parallel reading of multiple books.

[0070] Furthermore, the reading experience optimization system includes a unit that acquires user marker information and uses it as data for a publishing strategy. The marketing data acquisition unit uses generative AI to acquire user marker information and uses it as data for a publishing strategy. For example, the marketing data acquisition unit analyzes information such as which parts have been marked with many markers and which summaries are frequently read. The marketing data acquisition unit can use the user marker information to improve the publishing strategy. For example, if a particular chapter or paragraph has been marked with many markers, the marketing data acquisition unit determines that this part is important to readers and reflects this in future publishing strategies. The marketing data acquisition unit also understands readers' interests and collects data to provide content that is attractive to readers. In this way, the user's marker information can be acquired and used as marketing data for a publishing strategy, which can be useful for improving the publishing strategy.

[0071] The summary generation unit can estimate the reader's emotions and adjust the way the summary is expressed based on the estimated reader's emotions. The summary generation unit uses the generation AI to estimate the reader's emotions and adjust the way the summary is expressed based on the estimated reader's emotions. For example, if the reader is excited, the summary generation unit can estimate the emotion and generate a summary with more lively expression. Also, if the reader is relaxed, the summary generation unit can estimate the emotion and generate a summary with calm expression. Also, if the reader is tired, the summary generation unit can estimate the emotion and generate a summary with concise and easy-to-understand expression. This makes it possible to provide a more appropriate summary by adjusting the way the summary is expressed according to the reader's emotions.

[0072] The summary generation unit can analyze the reader's past reading history and select a summary generation method. The summary generation unit uses generation AI to analyze the reader's past reading history and select the optimal summary generation method. For example, the summary generation unit analyzes the genre of books the reader has read in the past and generates the optimal summary for books of the same genre. The summary generation unit can also analyze the difficulty of books the reader has read in the past and generate the optimal summary for books of the same difficulty level. The summary generation unit can also analyze the ratings of books the reader has read in the past and generate more detailed summaries for highly rated books. In this way, the optimal summary generation method can be selected by analyzing the reader's past reading history.

[0073] The summary generator can customize the content of the summary based on the reader's current areas of interest when generating the summary. The summary generator uses generation AI to customize the content of the summary based on the reader's current areas of interest when generating the summary. For example, the summary generator generates a summary that includes related information based on topics that the reader is currently interested in. The summary generator can also generate a summary that includes related information based on keywords that the reader has recently searched for. The summary generator can also generate a summary that includes related information based on articles or news that the reader has recently read. This makes it possible to provide more relevant summaries by customizing the content of the summary based on the reader's current areas of interest.

[0074] The summary generation unit can select a summary generation means according to the reader's input method when generating a summary. The summary generation unit uses the generation AI to select the optimal summary generation means according to the reader's input method (voice, text, image, etc.) when generating a summary. For example, if the reader uses voice input, the summary generation unit has the generation AI analyze the voice data and generate the optimal summary. Also, if the reader uses text input, the summary generation unit can have the generation AI analyze the text data and generate the optimal summary. Also, if the reader uses image input, the summary generation unit can have the generation AI analyze the image data and generate the optimal summary. This makes it possible to provide a more appropriate summary by selecting the optimal summary generation means according to the reader's input method.

[0075] The summary generation unit can estimate the reader's emotions and adjust the length of the summary based on the estimated reader's emotions. The summary generation unit uses the generation AI to estimate the reader's emotions and adjust the length of the summary based on the estimated reader's emotions. For example, if the reader is in a hurry, the generation AI can estimate the reader's emotions and generate a short summary that covers the main points. Alternatively, if the reader is relaxed, the summary generation unit can estimate the reader's emotions and generate a detailed summary. Alternatively, if the reader is excited, the generation AI can estimate the reader's emotions and generate a summary with visually stimulating effects. This allows the length of the summary to be adjusted according to the reader's emotions, making it possible to provide a more appropriate summary.

[0076] When generating summaries, the summary generation unit can prioritize generating highly relevant summaries by taking into account the reader's geographical location information. When generating summaries, the summary generation unit uses generation AI to prioritize generating highly relevant summaries by taking into account the reader's geographical location information. For example, if the reader is in a specific area, the summary generation unit can generate a summary that includes information related to that area. Also, if the reader is traveling, the summary generation unit can generate a summary that includes information related to the travel destination. Also, if the reader is in a specific city, the summary generation unit can generate a summary that includes information related to that city. This makes it possible to provide more appropriate summaries by prioritizing the generation of highly relevant summaries by taking into account the reader's geographical location information.

[0077] The summary generation unit can analyze the reader's social media activity when generating a summary and generate a relevant summary. The summary generation unit uses generation AI to analyze the reader's social media activity when generating a summary and generate a relevant summary. For example, the summary generation unit generates a summary that includes related information based on articles that the reader shared on social media. The summary generation unit can also generate a summary that includes related information based on accounts that the reader follows on social media. The summary generation unit can also generate a summary that includes related information based on posts that the reader "liked" on social media. In this way, it is possible to provide relevant summaries by analyzing the reader's social media activity.

[0078] The summary generation unit can customize the summary generation method by reflecting readers' past feedback when generating a summary. The summary generation unit uses generation AI to customize the summary generation method by reflecting readers' past feedback when generating a summary. For example, the summary generation unit generates the optimal summary based on summary generation methods that readers have previously rated highly. The summary generation unit can also generate the optimal summary by avoiding summary generation methods that readers have previously rated poorly. The summary generation unit can also customize the content and presentation of the summary based on feedback provided by readers in the past. This makes it possible to provide more appropriate summaries by reflecting readers' past feedback.

[0079] The marker function unit can estimate the reader's emotions and adjust the marker display method based on the estimated reader's emotions. The marker function unit uses the generation AI to estimate the reader's emotions and adjust the marker display method based on the estimated reader's emotions. For example, if the reader is excited, the generation AI can estimate the emotion and display a visually stimulating marker. Also, if the reader is relaxed, the marker function unit can estimate the emotion and display a marker with a calm color tone. Also, if the reader is tired, the generation AI can estimate the emotion and display a simple, highly visible marker. This makes it possible to provide more appropriate markers by adjusting the marker display method according to the reader's emotions.

[0080] When the marker function is used, the marker function unit can analyze the reader's past marker history and select the optimal marker display method. When the marker function is used, the marker function unit uses generation AI to analyze the reader's past marker history and select the optimal marker display method. For example, the marker function unit displays the optimal marker based on the marker color and style used by the reader in the past. The marker function unit can also analyze the trends in the places where readers have marked in the past and display markers in related places. The marker function unit can also display the optimal marker based on the display method of markers that the reader has given high ratings to in the past. In this way, the optimal marker display method can be selected by analyzing the reader's past marker history.

[0081] The marker function unit can customize the range of markers based on the reader's current reading situation when using the marker function. The marker function unit uses generation AI to customize the range of markers based on the reader's current reading situation when using the marker function. For example, if a reader is reading a specific chapter, the marker function unit can display markers in ranges related to that chapter. Also, if a reader is concentrating on a specific topic, the marker function unit can display markers in ranges related to that topic. Also, if a reader is searching for a specific keyword, the marker function unit can display markers in ranges related to that keyword. This makes it possible to provide more appropriate markers by customizing the range of markers based on the reader's current reading situation.

[0082] The marker function unit can select the optimal marker display means depending on the reader's input method when using the marker function. The marker function unit uses the generation AI to select the optimal marker display means depending on the reader's input method (voice, text, image, etc.) when using the marker function. For example, if the reader is using voice input, the marker function unit can have the generation AI analyze the voice data and display the optimal marker. Also, if the reader is using text input, the marker function unit can have the generation AI analyze the text data and display the optimal marker. Also, if the reader is using image input, the marker function unit can have the generation AI analyze the image data and display the optimal marker. This makes it possible to provide more appropriate markers by selecting the optimal marker display means depending on the reader's input method.

[0083] The marker function unit can estimate the reader's emotions and determine the priority of markers based on the estimated reader's emotions. The marker function unit uses the generation AI to estimate the reader's emotions and determine the priority of markers based on the estimated reader's emotions. For example, if the reader is excited, the generation AI can estimate the emotion and prioritize markers on important sections. Also, if the reader is relaxed, the marker function unit can estimate the emotion and prioritize markers on highly relevant sections. Also, if the reader is tired, the generation AI can estimate the emotion and prioritize markers on concise and easy-to-understand sections. This makes it possible to provide more appropriate markers by determining the priority of markers according to the reader's emotions.

[0084] When the marker function is used, the marker function unit can prioritize displaying highly relevant markers by taking into consideration the reader's geographical location information. When the marker function is used, the marker function unit uses generation AI to prioritize displaying highly relevant markers by taking into consideration the reader's geographical location information. For example, if the reader is in a specific area, the marker function unit can display markers containing information related to that area. Also, if the reader is traveling, the marker function unit can display markers containing information related to the travel destination. Also, if the reader is in a specific city, the marker function unit can display markers containing information related to that city. This makes it possible to provide more appropriate markers by prioritize displaying highly relevant markers by taking into consideration the reader's geographical location information.

[0085] The marker function unit can analyze the reader's social media activity and display related markers when the marker function is used. The marker function unit uses generation AI to analyze the reader's social media activity and display related markers when the marker function is used. For example, the marker function unit displays markers containing related information based on articles the reader has shared on social media. The marker function unit can also display markers containing related information based on accounts the reader follows on social media. The marker function unit can also display markers containing related information based on posts the reader has "liked" on social media. In this way, related markers can be provided by analyzing the reader's social media activity.

[0086] The marker function unit can customize the marker display method by reflecting readers' past feedback when the marker function is used. The marker function unit uses generation AI to customize the marker display method by reflecting readers' past feedback when the marker function is used. For example, the marker function unit displays the most appropriate marker based on the display method of markers that readers have previously rated highly. The marker function unit can also display the most appropriate marker by avoiding the display method of markers that readers have previously rated poorly. The marker function unit can also customize the content and display method of markers based on feedback provided by readers in the past. This makes it possible to provide more appropriate markers by reflecting readers' past feedback.

[0087] The expression change unit can estimate the reader's emotions and adjust the method of expression change based on the estimated reader's emotions. The expression change unit uses the generation AI to estimate the reader's emotions and adjust the method of expression change based on the estimated reader's emotions. For example, if the reader is excited, the generation AI can estimate the emotion and change the expression to a more visually stimulating one. Also, if the reader is relaxed, the generation AI can estimate the emotion and change the expression to a calmer one. Also, if the reader is tired, the generation AI can estimate the emotion and change the expression to a concise and easy-to-understand one. In this way, by adjusting the method of expression change according to the reader's emotions, more appropriate expressions can be provided.

[0088] The expression modification unit can customize the expression based on the reader's current level of understanding when changing the expression. The expression modification unit uses the generation AI to customize the expression based on the reader's current level of understanding when changing the expression. For example, if the reader has a low level of understanding of a particular topic, the expression modification unit causes the generation AI to change the expression to a simpler one. Also, if the reader has a high level of understanding of a particular topic, the expression modification unit can cause the generation AI to change the expression to a more detailed one. Also, if the reader has a medium level of understanding of a particular topic, the expression modification unit can cause the generation AI to change the expression to one with an appropriate level of detail. In this way, by customizing the expression based on the reader's current level of understanding, more appropriate expression can be provided.

[0089] The expression change unit can select the optimal expression change means depending on the reader's input method when changing an expression. The expression change unit uses the generation AI to select the optimal expression change means depending on the reader's input method (voice, text, image, etc.) when changing an expression. For example, if the reader uses voice input, the expression change unit has the generation AI analyze the voice data and change the expression to the optimal expression. Also, if the reader uses text input, the expression change unit can have the generation AI analyze the text data and change the expression to the optimal expression. Also, if the reader uses image input, the generation AI can analyze the image data and change the expression to the optimal expression. In this way, by selecting the optimal expression change means depending on the reader's input method, more appropriate expressions can be provided.

[0090] The expression change unit can estimate the reader's emotions and determine the priority of expression changes based on the estimated reader's emotions. The expression change unit uses the generation AI to estimate the reader's emotions and determine the priority of expression changes based on the estimated reader's emotions. For example, if the reader is excited, the generation AI can estimate the emotion and prioritize changing the expression of important parts. Also, if the reader is relaxed, the expression change unit can estimate the emotion and prioritize changing the expression of highly relevant parts. Also, if the reader is tired, the generation AI can estimate the emotion and prioritize changing the expression of concise and easy-to-understand parts. In this way, by determining the priority of expression changes according to the reader's emotions, more appropriate expressions can be provided.

[0091] When changing expressions, the expression change unit can prioritize changing highly relevant expressions taking into account the reader's geographical location information. When changing expressions, the expression change unit uses generation AI to prioritize changing highly relevant expressions taking into account the reader's geographical location information. For example, if the reader is in a specific area, the expression change unit can prioritize changing expressions that include information related to that area. Also, if the reader is traveling, the expression change unit can prioritize changing expressions that include information related to the travel destination. Also, if the reader is in a specific city, the expression change unit can prioritize changing expressions that include information related to that city. In this way, by prioritizing changing highly relevant expressions taking into account the reader's geographical location information, more appropriate expressions can be provided.

[0092] The expression change unit can analyze the reader's social media activity and change the relevant expression when changing the expression. The expression change unit uses generative AI to analyze the reader's social media activity and change the relevant expression when changing the expression. For example, the expression change unit changes the expression including relevant information based on articles the reader shared on social media. The expression change unit can also change the expression including relevant information based on accounts the reader follows on social media. The expression change unit can also change the expression including relevant information based on posts the reader "liked" on social media. In this way, relevant expression can be provided by analyzing the reader's social media activity.

[0093] The expression change unit can customize the expression change method by reflecting readers' past feedback when changing expressions. The expression change unit uses a generation AI to customize the expression change method by reflecting readers' past feedback when changing expressions. For example, the expression change unit changes the most appropriate expression based on expression change methods that readers have given high ratings to in the past. The expression change unit can also change the most appropriate expression by avoiding expression change methods that readers have given low ratings to in the past. The expression change unit can also customize the content of the expression and the change method based on feedback provided by readers in the past. This makes it possible to provide more appropriate expressions by reflecting readers' past feedback.

[0094] The parallel reading support unit can estimate the reader's emotions and adjust the parallel reading support method based on the estimated reader's emotions. The parallel reading support unit uses a generation AI to estimate the reader's emotions and adjust the parallel reading support method based on the estimated reader's emotions. For example, if the parallel reading support unit is excited, the generation AI can estimate the reader's emotions and provide support by emphasizing the relationships between multiple books. Also, if the reader is relaxed, the generation AI can estimate the reader's emotions and support parallel reading at a gentle pace. Also, if the reader is tired, the generation AI can estimate the reader's emotions and provide concise and easy-to-understand support. This makes it possible to provide more appropriate support by adjusting the parallel reading support method according to the reader's emotions.

[0095] The parallel reading support unit can analyze the reader's past reading history and select the optimal support method when supporting parallel reading. The parallel reading support unit uses generative AI to analyze the reader's past reading history and select the optimal support method when supporting parallel reading. For example, the parallel reading support unit analyzes the genre of books the reader has read in the past and provides the optimal support for books of the same genre. The parallel reading support unit can also analyze the difficulty level of books the reader has read in the past and provide the optimal support for books of the same difficulty level. The parallel reading support unit can also analyze the ratings of books the reader has read in the past and provide more detailed support for highly rated books. In this way, the optimal support method can be selected by analyzing the reader's past reading history.

[0096] The parallel reading support unit can customize the support content based on the reader's current reading situation when supporting parallel reading. The parallel reading support unit uses generative AI to customize the support content based on the reader's current reading situation when supporting parallel reading. For example, if the reader is reading a specific chapter, the parallel reading support unit can provide information related to that chapter. Also, if the reader is concentrating on a specific topic, the parallel reading support unit can provide information related to that topic. Also, if the reader is searching for a specific keyword, the parallel reading support unit can provide information related to that keyword. This allows the support content to be customized based on the reader's current reading situation, making it possible to provide more appropriate support.

[0097] The parallel reading support unit can estimate the reader's emotions and determine the priority of parallel reading based on the estimated reader's emotions. The parallel reading support unit uses a generation AI to estimate the reader's emotions and determine the priority of parallel reading based on the estimated reader's emotions. For example, if the parallel reading support unit is excited, the generation AI can estimate the reader's emotions and prioritize support for important passages. Also, if the reader is relaxed, the parallel reading support unit can estimate the reader's emotions and prioritize support for highly relevant passages. Also, if the reader is tired, the generation AI can estimate the reader's emotions and prioritize support for concise and easy-to-understand passages. This allows for more appropriate support by determining the priority of parallel reading based on the reader's emotions.

[0098] The parallel reading support unit can prioritize providing highly relevant support by taking into account the reader's geographical location information when supporting parallel reading. The parallel reading support unit uses generation AI to prioritize providing highly relevant support by taking into account the reader's geographical location information when supporting parallel reading. For example, if the reader is in a specific area, the parallel reading support unit can provide information related to that area. Also, if the reader is traveling, the parallel reading support unit can provide information related to the travel destination. Also, if the reader is in a specific city, the parallel reading support unit can provide information related to that city. This makes it possible to provide more appropriate support by prioritizing highly relevant support by taking into account the reader's geographical location information.

[0099] The parallel reading support unit can analyze the reader's social media activity and provide relevant support during parallel reading support. The parallel reading support unit uses generative AI to analyze the reader's social media activity and provide relevant support during parallel reading support. For example, the parallel reading support unit can provide relevant information based on articles the reader has shared on social media. The parallel reading support unit can also provide relevant information based on accounts the reader follows on social media. The parallel reading support unit can also provide relevant information based on posts the reader has "liked" on social media. In this way, relevant support can be provided by analyzing the reader's social media activity.

[0100] The marketing data acquisition unit can estimate the reader's emotions and adjust the method of acquiring marketing data based on the estimated reader's emotions. The marketing data acquisition unit uses the generation AI to estimate the reader's emotions and adjust the method of acquiring marketing data based on the estimated reader's emotions. For example, if the reader is excited, the marketing data acquisition unit can have the generation AI estimate the emotion and prioritize acquiring important data. Also, if the reader is relaxed, the marketing data acquisition unit can have the generation AI estimate the emotion and prioritize acquiring highly relevant data. Also, if the reader is tired, the generation AI can estimate the emotion and prioritize acquiring concise, easy-to-understand data. This makes it possible to acquire more appropriate data by adjusting the method of acquiring marketing data according to the reader's emotions.

[0101] When acquiring marketing data, the marketing data acquisition unit can analyze the reader's past marker history and select the optimal data acquisition method. When acquiring marketing data, the marketing data acquisition unit uses the generation AI to analyze the reader's past marker history and select the optimal data acquisition method. For example, the marketing data acquisition unit acquires optimal data based on the marker colors and styles used by the reader in the past. The marketing data acquisition unit can also analyze trends in areas that readers have highlighted in the past and acquire related data. The marketing data acquisition unit can also acquire optimal data based on data on markers that readers have given high ratings to in the past. In this way, the optimal data acquisition method can be selected by analyzing the reader's past marker history.

[0102] The marketing data acquisition unit can customize the data acquisition content based on the reader's current reading status when acquiring marketing data. The marketing data acquisition unit uses the generation AI to customize the data acquisition content based on the reader's current reading status when acquiring marketing data. For example, if a reader is reading a specific chapter, the marketing data acquisition unit can acquire data related to that chapter. Also, if a reader is concentrating on a specific topic, the marketing data acquisition unit can also acquire data related to that topic. Also, if a reader is searching for a specific keyword, the marketing data acquisition unit can acquire data related to that keyword. In this way, by customizing the data acquisition content based on the reader's current reading status, more appropriate data can be acquired.

[0103] The marketing data acquisition unit can estimate the reader's emotions and prioritize marketing data based on the estimated reader's emotions. The marketing data acquisition unit uses the generation AI to estimate the reader's emotions and prioritizes marketing data based on the estimated reader's emotions. For example, if the reader is excited, the marketing data acquisition unit can have the generation AI estimate the emotion and prioritize acquiring important data. Also, if the reader is relaxed, the marketing data acquisition unit can have the generation AI estimate the emotion and prioritize acquiring highly relevant data. Also, if the reader is tired, the generation AI can estimate the emotion and prioritize acquiring concise and easy-to-understand data. This allows more appropriate data to be acquired by prioritizing marketing data according to the reader's emotions.

[0104] The marketing data acquisition unit can analyze readers' social media activities and acquire related data when acquiring marketing data. The marketing data acquisition unit uses generative AI to analyze readers' social media activities and acquire related data when acquiring marketing data. For example, the marketing data acquisition unit acquires related data based on articles shared by readers on social media. The marketing data acquisition unit can also acquire related data based on accounts that readers follow on social media. The marketing data acquisition unit can also acquire related data based on posts that readers "like" on social media. In this way, related data can be acquired by analyzing readers' social media activities.

[0105] The marketing data acquisition unit can customize the data acquisition method by reflecting readers' past feedback when acquiring marketing data. The marketing data acquisition unit uses generative AI to customize the data acquisition method by reflecting readers' past feedback when acquiring marketing data. For example, the marketing data acquisition unit acquires optimal data based on data acquisition methods that readers have given high ratings to in the past. The marketing data acquisition unit can also acquire optimal data by avoiding data acquisition methods that readers have given low ratings to in the past. The marketing data acquisition unit can also customize the content of data and the acquisition method based on feedback provided by readers in the past. This makes it possible to acquire more appropriate data by reflecting readers' past feedback. === Hard Collateral 1-1 === Each of the above-described elements, including the summary generation unit, marker function unit, expression change unit, parallel reading support unit, and marketing data acquisition unit, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the summary generation unit is implemented by either the smart device 14 or the data processing device 12. For example, the control unit 46A of the smart device 14 can use a generation AI to generate summaries tailored to the reader's knowledge level. The marker function unit is implemented, for example, by the control unit 46A of the smart device 14, and generates summaries for specific chapters or paragraphs when the reader highlights them. The expression change unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and uses a generation AI to change difficult-to-understand passages into simpler expressions. The parallel reading support unit is implemented, for example, by the control unit 46A of the smart device 14, and links points from previously purchased books with the book currently being read. The marketing data acquisition unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and acquires user marker information and uses it as data for publishing strategies. === Hard Collateral 1-2 === Each of the above-described elements, including the summary generation unit, marker function unit, expression change unit, parallel reading support unit, and marketing data acquisition unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the summary generation unit is implemented by either the smart glasses 214 or the data processing device 12. For example, the control unit 46A of the smart glasses 214 can use a generation AI to generate summaries tailored to the reader's knowledge level. The marker function unit is implemented, for example, by the control unit 46A of the smart glasses 214, and generates summaries for specific chapters or paragraphs when the reader highlights them. The expression change unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and uses a generation AI to change difficult-to-understand passages into simpler expressions. The parallel reading support unit is implemented, for example, by the control unit 46A of the smart glasses 214, and links points from previously purchased books to the book currently being read. The marketing data acquisition unit is realized by, for example, the specific processing unit 290 of the data processing device 12, acquires the user's marker information, and utilizes it as data for the publishing strategy. === Hard Collateral 1-3 === Each of the above-described elements, including the summary generator, marker function unit, expression change unit, parallel reading support unit, and marketing data acquisition unit, is implemented, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the summary generator is implemented by either the headset terminal 314 or the data processing device 12. For example, the control unit 46A of the headset terminal 314 can use a generation AI to generate summaries tailored to the reader's knowledge level. The marker function unit is implemented, for example, by the control unit 46A of the headset terminal 314, and generates summaries for specific chapters or paragraphs when the reader highlights them. The expression change unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and uses a generation AI to change difficult-to-understand passages into simpler expressions. The parallel reading support unit is implemented, for example, by the control unit 46A of the headset terminal 314, and links points from previously purchased books to the book currently being read. The marketing data acquisition unit is realized by, for example, the specific processing unit 290 of the data processing device 12, acquires the user's marker information, and utilizes it as data for the publishing strategy. === Hard Collateral 1-4 === Each of the above-described elements, including the summary generation unit, marker function unit, expression change unit, parallel reading support unit, and marketing data acquisition unit, is implemented, for example, by at least one of the robot 414 and the data processing device 12. For example, the summary generation unit is implemented by either the robot 414 or the data processing device 12. For example, the control unit 46A of the robot 414 can use a generation AI to generate summaries tailored to the reader's knowledge level. The marker function unit is implemented, for example, by the control unit 46A of the robot 414, and generates summaries for specific chapters or paragraphs when the reader highlights them. The expression change unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and uses a generation AI to change difficult-to-understand passages into simpler expressions. The parallel reading support unit is implemented, for example, by the control unit 46A of the robot 414, and links points from previously purchased books with the book currently being read. The marketing data acquisition unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and acquires user marker information and uses it as data for publishing strategies.

[0106] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0107] The reading experience optimization system can further include a speed adjustment unit that measures the reader's reading speed and adjusts the level of detail in the summary according to the speed. For example, if the reader is reading quickly, the speed adjustment unit can use a generation AI to generate a concise summary that covers the main points. On the other hand, if the reader is reading slowly, the speed adjustment unit can also generate a detailed summary. Furthermore, if the reader stops at a particular point, it can provide additional information related to that point. This makes it possible to provide a more appropriate reading experience by adjusting the level of detail in the summary according to the reader's reading speed.

[0108] The reading experience optimization system may further include an eye-tracking unit that acquires eye-tracking data of the reader and adjusts the summary generation method based on the eye movements. For example, if the reader focuses their eyes on a particular passage, the eye-tracking unit may generate a detailed summary related to that passage. If the reader moves their eyes frequently, the eye-tracking unit may generate a concise summary that covers the main points. Furthermore, if the reader fixates their eyes for a long time, the eye-tracking unit may provide additional information related to that passage. In this way, a more appropriate reading experience can be provided by adjusting the summary generation method based on the reader's eye movements.

[0109] The reading experience optimization system can further include a speech analyzer that analyzes the reader's speech input and adjusts the summary generation method based on the tone and speed of the speech. For example, if the reader is speaking in an excited tone, the speech analyzer can generate a summary using lively expressions. On the other hand, if the reader is speaking in a calm tone, the speech analyzer can also generate a summary using calm expressions. Furthermore, if the reader is speaking quickly, the speech analyzer can also generate a concise summary. In this way, a more appropriate reading experience can be provided by adjusting the summary generation method based on the reader's speech input.

[0110] The reading experience optimization system can further include a heart rate analysis unit that measures the reader's heart rate and adjusts the summary generation method based on the heart rate. For example, if the reader's heart rate is high, the heart rate analysis unit can use a generation AI to generate a summary with stimulating language. If the reader's heart rate is low, the heart rate analysis unit can also generate a summary with calm language. Furthermore, if the reader's heart rate is stable, the heart rate analysis unit can generate a detailed summary. This makes it possible to provide a more appropriate reading experience by adjusting the summary generation method based on the reader's heart rate.

[0111] The reading experience optimization system can further include an expression analysis unit that analyzes the reader's facial expression and adjusts the summary generation method based on the facial expression. For example, if the reader is smiling, the expression analysis unit uses the generation AI to generate a summary with a cheerful expression. If the reader has a serious expression, the expression analysis unit can also generate a detailed summary. Furthermore, if the reader has a confused expression, the expression analysis unit can also generate a concise and easy-to-understand summary. This makes it possible to provide a more appropriate reading experience by adjusting the summary generation method based on the reader's facial expression.

[0112] The reading experience optimization system can further include an environment detection unit that detects the reader's reading environment and adjusts the summary generation method according to the environment. For example, if the reader is in a quiet environment, the environment detection unit can use the generation AI to generate a detailed summary. If the reader is in a noisy environment, the environment detection unit can also generate a concise summary. Furthermore, if the reader is on the move, the environment detection unit can also generate a summary that focuses on the main points. This allows for a more appropriate reading experience by adjusting the summary generation method according to the reader's reading environment.

[0113] The reading experience optimization system can further include a device detection unit that detects the device usage status of the reader and adjusts the summary generation method according to the usage status. For example, if the reader is using a smartphone, the device detection unit can use the generation AI to generate a concise summary. If the reader is using a tablet, the device detection unit can also generate a detailed summary. Furthermore, if the reader is using a PC, the device detection unit can also generate a visually rich summary. This makes it possible to provide a more appropriate reading experience by adjusting the summary generation method according to the device usage status of the reader.

[0114] The reading experience optimization system can further include a cloud synchronization unit that stores the reader's reading history on the cloud and makes it accessible from other devices. For example, if a reader continues reading a book on a tablet after having been reading it on a smartphone, the cloud synchronization unit synchronizes the reading history so that the reader can resume reading from the same place. The cloud synchronization unit can also synchronize the reading history if the reader continues reading a book on a smartphone after having been reading it on a computer. Furthermore, if the reader purchases a new device, the cloud synchronization unit can synchronize the reading history. This allows the reader's reading history to be stored on the cloud and be accessible from other devices, providing a more convenient reading experience.

[0115] The reading experience optimization system can further include a time adjustment unit that measures the reader's reading time and adjusts the summary generation method according to the time. For example, if the reader reads for a short time, the time adjustment unit uses a generation AI to generate a concise summary that covers the main points. On the other hand, if the reader reads for a long time, the time adjustment unit can also generate a detailed summary. Furthermore, if the reader reads at a specific time of day, it can also generate a summary appropriate for that time of day. This makes it possible to provide a more appropriate reading experience by adjusting the summary generation method according to the reader's reading time.

[0116] The reading experience optimization system can further include a habit learning unit that learns the reader's reading habits and adjusts the summary generation method based on the habits. For example, if a reader reads at a specific time every day, the habit learning unit can generate summaries that are optimal for that time. Also, if a reader reads for long periods on weekends, the habit learning unit can generate detailed summaries. Furthermore, if a reader prefers to read books of a specific genre, it can generate summaries that are appropriate for that genre. In this way, a more appropriate reading experience can be provided by adjusting the summary generation method based on the reader's reading habits.

[0117] The processing flow of the second embodiment will be briefly explained below.

[0118] Step 1: The summary generator uses AI to generate summaries tailored to the reader's knowledge level. The reader's knowledge level is determined based on their reading history within the app and their input information. For example, summaries tailored to the reader's level are generated, such as summaries for beginners, intermediate readers, and advanced readers. Step 2: The marker function uses the generation AI to highlight specific sections of the summary generated by the summary generator. For example, if a reader highlights a specific chapter or paragraph, a summary of that section will be generated. This allows the reader to efficiently dig deeper into the parts of the text that interest them and easily reread them later. Step 3: The expression modification unit uses the generation AI to change any difficult-to-understand parts of the summary generated by the summary generation unit into simpler expressions. For example, the generation AI can replace parts containing technical terms or difficult expressions with simpler words, making them easier for readers to understand.

[0119] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0120] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0121] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0122] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0123] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0124] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0125] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0126] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0127] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0128] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0129] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0130] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0131] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0132] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0133] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0134] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0135] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0136] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0137] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0138] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0139] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0140] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0141] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0142] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0143] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0144] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0145] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0146] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0147] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0148] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0149] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0150] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0151] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0153] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0154] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0155] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0156] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0157] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0158] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0159] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0160] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0161] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0162] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0163] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0164] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0165] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0166] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0167] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0168] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0169] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0170] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0171] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0172] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0173] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0174] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0175] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0176] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0177] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0178] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0179] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0180] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0181] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0182] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0183] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0184] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0185] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0186] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0187] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0188] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0189] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0190] [Explanation of symbols]

[0191] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a summary generator for generating summaries according to the reader's knowledge level; a marker function unit that marks a specific range of the summary generated by the summary generation unit; a unit for generating a summary of the range marked by the marker function unit; an expression modification unit that modifies difficult-to-understand parts of the summary generated by the summary generation unit into simpler expressions; Equipped with A system characterized by:

2. Equipped with a section that supports reading multiple books at the same time 2. The system of claim 1.

3. Equipped with a department that acquires user marker information and uses it as data for publishing strategies 2. The system of claim 1.

4. The summary generation unit Estimate the reader's sentiment and adjust the summary presentation based on the estimated sentiment 2. The system of claim 1.

5. The summary generation unit Analyze the reader's past reading history and select a summary generation method 2. The system of claim 1.

6. The summary generation unit Customize summary content based on the reader's current interests when generating the summary 2. The system of claim 1.

7. The summary generation unit When generating a summary, select a summary generation method based on the reader's input method.

2. The system of claim 1.

8. The summary generation unit Estimate reader sentiment and adjust summary length based on estimated reader sentiment 2. The system of claim 1.

9. The summary generation unit When generating summaries, the system takes into account the reader's geographic location to prioritize the most relevant summaries.

2. The system of claim 1.

10. The summary generation unit When generating summaries, analyze readers' social media activity and generate relevant summaries.

2. The system of claim 1.

Images